1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
|
"""
=================================================
Demo of affinity propagation clustering algorithm
=================================================
Reference:
Brendan J. Frey and Delbert Dueck, "Clustering by Passing Messages
Between Data Points", Science Feb. 2007
"""
import numpy as np
from sklearn import metrics
from sklearn.cluster import AffinityPropagation
from sklearn.datasets import make_blobs
# %%
# Generate sample data
# --------------------
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(
n_samples=300, centers=centers, cluster_std=0.5, random_state=0
)
# %%
# Compute Affinity Propagation
# ----------------------------
af = AffinityPropagation(preference=-50, random_state=0).fit(X)
cluster_centers_indices = af.cluster_centers_indices_
labels = af.labels_
n_clusters_ = len(cluster_centers_indices)
print("Estimated number of clusters: %d" % n_clusters_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f" % metrics.adjusted_rand_score(labels_true, labels))
print(
"Adjusted Mutual Information: %0.3f"
% metrics.adjusted_mutual_info_score(labels_true, labels)
)
print(
"Silhouette Coefficient: %0.3f"
% metrics.silhouette_score(X, labels, metric="sqeuclidean")
)
# %%
# Plot result
# -----------
import matplotlib.pyplot as plt
plt.close("all")
plt.figure(1)
plt.clf()
colors = plt.cycler("color", plt.cm.viridis(np.linspace(0, 1, 4)))
for k, col in zip(range(n_clusters_), colors):
class_members = labels == k
cluster_center = X[cluster_centers_indices[k]]
plt.scatter(
X[class_members, 0], X[class_members, 1], color=col["color"], marker="."
)
plt.scatter(
cluster_center[0], cluster_center[1], s=14, color=col["color"], marker="o"
)
for x in X[class_members]:
plt.plot(
[cluster_center[0], x[0]], [cluster_center[1], x[1]], color=col["color"]
)
plt.title("Estimated number of clusters: %d" % n_clusters_)
plt.show()
|
